$4.[15$ points$]$ The feedforward neural network in the figure below has four input units, two neurons

in the hidden layer and one neuron in the output layer. The neurons in the network do not have bias

inputs and bias weights. All four connections between the input layer and the hidden layer have a

weight value of $0\mathrm{.}1$ and the two connections between the hidden layer and the output layer have a

weight value of $0\mathrm{.}2.$ The ReLU function is used as the activation function in neurons $5$ and $6$ and the

Sigmoid $($or Logistic$)$ function is used as the activation function in neuron $7.$ The input values for the

four input units are $($a$1,$ a$2,$ a$3,$ a$4)=(1\mathrm{.}0,1\mathrm{.}5,-2\mathrm{.}0,-2\mathrm{.}5).$ Compute the output values for neurons a$5,$

a$6$ and a$7.$ Show all work to get full credits.